探索性因素分析——最近10年的评述

目的：(1)介绍国外心理统计学界对探索性因素分析中几个重大问题的基本观点；(2)系统地评述过去10年里(1991～2000年)我国心理学研究对这一技术的使用情况；(3)强调运用这一技术时值得注意的一些事项，以期这一技术对我国心理学研究发挥更大的作用。方法：作检索了《心理学报》和《心理科学》在1991～2000年间与探索性因素分析有关的章，对其中以探索性因素分析为主要研究方法的重点章(feature article)进行了编码，统计了频数及百分比分布。结果：我国心理学研究在积极使用探索性因素分析这一先进统计技术时还存在一些问题，主要表现在：(1)在确定因素个数时，倾向于机械地依靠桌个单一方法来作决定，(2)大量使用正交旋转，(3)过于依赖SPSS，(4)对因素分析过程中的重要信息／结果报告不够。结论：探索性因素分析在过去十年得到了广泛的应用，如能吸收国外同行的一些观点，探索性因素分析这一技术在我国心理学研究中必将获得更广泛有效的应用。

Exploratory Factor Analysis: A Literature Review Between 1991 and 2000

The purposes of this article was to: 1) clarify some confusing issues in exploratory factor analysis (EFA) among Chinese psychologists, and 2) critically review how Chinese psychologists have been applying EFA in their research during the last decade (1991~2000). In the first part of this article, the following issues were discussed: (a) estimating the number of common factors, (b) the rotation problem, and (c) the myth of simple structure. The authors searched Psychological Science and Acta Psychologica Sinica between 1991~2000 and identified 95 EFAs from feature articles that used EFA as their major quantitative method. All the identified EFAs are coded on the following characteristics: (a) scale reliability, (b) ratio of item number to factor number, (c) ratio of sample to item number, (d) sample size, (e) methods to determine number of factors, (f) rotation method, (g) software, and (h) report practice. Simple statistics such as, frequency and percentage, revealed the major problems many Chinese psychologists have in employing EFA include: (a) exclusive reliance on some mechanical methods to determine factor numbers, (b) using orthogonal rotation without justification, (c) overuse of SPSS, and (d) failure to report major information and results so that peer-evaluation is essentially impossible. The possible reasons for the current situation are discussed.